# mcp-docs-assistant

> mcp-docs-assistant — imanshrajsingh-boost-mcp-docs-rag-assistant. Use this tool when you need to retrieve accurate and secure information about the Model Context Protocol through natural-language queries. It solves problems related to information retrieval, data privacy, and model understanding by providing grounded answers with features like PII masking and hallucination detection. The mcp-docs-assistant takes in natural-language questions as input and outputs relevant, secure, and reliable information.

Canonical page: https://skillsregistry.net/skills/imanshrajsingh-boost-mcp-docs-rag-assistant  
JSON: https://api.skillsregistry.net/v1/skills/imanshrajsingh-boost-mcp-docs-rag-assistant

## Description

It lets MCP clients such as Claude Desktop ask natural-language questions about the Model Context Protocol and get grounded answers with reranking, semantic caching, guardrails, PII masking, and hallucination detection.

## Trust

- **Trust score (0–1):** 0.67
- **Verification tier:** scanned
- **Last scanned:** 2026-09-04

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-09-04

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/oeryxryl8p)
- **Repository:** <https://github.com/imanshrajsingh-boost/mcp-docs-rag-assistant>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "imanshrajsingh-boost-mcp-docs-rag-assistant"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/imanshrajsingh-boost-mcp-docs-rag-assistant` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/imanshrajsingh-boost-mcp-docs-rag-assistant/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt